© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 466
    Prev
    Next
    INDEX
    Explanations

    Connectors, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    new
    -0.85
     MainAxisSize
    -0.85
     new
    -0.81
     nowo
    -0.79
     nueva
    -0.78
    新
    -0.77
     الجديد
    -0.75
    NEW
    -0.73
    の新
    -0.73
     novo
    -0.73
    POSITIVE LOGITS
     different
    0.58
    HtmlAttribute
    0.56
     revisit
    0.54
     stronger
    0.54
    IActionResult
    0.53
     greater
    0.51
     expanded
    0.51
    tadır
    0.50
    不一样的
    0.50
     amended
    0.49
    Activations Density 0.006%

    No Known Activations